Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to advertisements and brand integrity in relation to explicit content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    context and association

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Explanation
    -0.41
     Clark
    -0.39
     exponent
    -0.39
     division
    -0.39
     advisor
    -0.37
    گو
    -0.36
    explanation
    -0.36
    сели
    -0.36
    issimi
    -0.36
    exponent
    -0.36
    POSITIVE LOGITS
     Reſ
    0.59
    principalColumn
    0.57
     fubject
    0.50
     ſen
    0.47
     Inſ
    0.45
     ſche
    0.44
     pleaſure
    0.44
    InstrumentedTest
    0.43
     poffible
    0.43
    DIPSETTING
    0.43
    Act Density 0.140%

    No Known Activations